In this survey, we argue that using structured vocabularies is capital to the success of image
annotation. We analyze literature on image annotation uses and user needs, and we stress …

This paper proposes a Feed-forward Neural Network (FNN) based method to combine word-
to-word semantic similarity metrics for improving the accuracy of image annotation. The …

Impoverished syntax and nondifferentiable vocabularies make natural language a poor
medium for neural representation learning and applications. Learned, quasilinguistic neural …

This dissertation proposes a new methodology for building and using structured knowledge
models for automatic image annotation. Specifically, our first proposals deal with the …

The objective of this document is to introduce the principle of Autonomous PErceptual
System (APES) as an object of study. The functionalities of artificial perception, in particular …

Visual foveation is the association of a spatially variant resolution sensor–the retina–and a
dynamic controlled mechanism for directing the area of maximal acuity. This paper …

Cette thèse, réalisée en coopération avec l'ONERA, concerne la reconnaissance active
d'objets 3D par un agent autonome muni d'une caméra d'observation. Alors qu'en …

Publication & Citation List Page 1 Publication & Citation List Yannis Avrithis February 26, 2013
Contents 1 Introduction 1 2 Publications 2 2.1 Theses …

Vehicle Recognition in Video Surveillance Page 1 Chapter 11 Vehicle Recognition in Video
Surveillance 11.1. Introduction Vehicles are objects of major interest for video surveillance. To …